Bayesian Inverse Problems

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 78

All topics

Uncovering and Fixing Collider Bias in Bayesian PINNs
Oct 8, 2026Michael Obermayr, Robert PeharzPhysics-Informed ML Bayesian Inverse Problems
TU Graz
Kinetic Langevin Meets Split Gibbs: Accelerated Posterior Sampling for Imaging Inverse Problems with Diffusion Priors
Oct 7, 2026Dai Hai Nguyen, Duc Dung NguyenBayesian Inverse Problems Markov Chain Monte Carlo
Hokkaido University · Institute of Information Technology, VAST
Self-attention summary networks for subsurface velocity-model building from common-image gathers
Oct 7, 2026Shiqin Zeng, Yunlin Zeng, Abhinav Prakash Gahlot +2Inverse Problems Bayesian Inverse Problems
Georgia Institute of Technology
Twist Flow for Inverse Problems
Oct 7, 2026Shiqin Zeng, Zijun Deng, Felix J. HerrmannBayesian Inverse Problems Posterior Sampling
Georgia Institute of Technology
BAM! Bayesian Anything Model: a foundation model for generative computational imaging
Sep 30, 2026Alessio Spagnoletti, Charlesquin Kemajou Mbakam, Jonathan Spence +2Physics-Informed Generative Modeling Physics-Guided Image Restoration
Laboratoire MAP5, UMR 8145, Université Paris Cité, CNRS · Heriot-Watt University, School of Mathematical and Computer Sciences & Maxwell Institute for Mathematical Sciences
Principled MAP estimation for inverse problems: bridging the gap between convergence and performance
Sep 29, 2026Alexandre Lagier, Valentine Tosel, Anne Gagneux +2Bayesian Inverse Problems Bayesian Inference
ENS de Lyon, CNRS, Université Claude Bernard Lyon 1, Inria, LIP UMR 5668, 69342 Lyon Cedex 07, France · Univ. Bordeaux, Inria, Bordeaux INP, IMB, UMR 5251, F-33400 Talence, France · Inria, ENS de Lyon, CNRS, Université Claude Bernard Lyon 1, LIP UMR 5668, 69342 Lyon Cedex 07, France
Simulation-Based Inference for Plate Reverb System Identification
Sep 28, 2026Dylan Sechet, Marc Evrard, Matthieu KowalskiParameter Estimation Bayesian Inverse Problems
Laboratoire Interdisciplinaire des Sciences du Numérique Université Paris-Saclay, Inria, CNRS, CentraleSupélec
FB-GDM: Fully-Bayesian Guided Diffusion Models for High-Dimensional Linear Inverse Problems via Unsupervised Variational Inference
Sep 24, 2026Gatien Séguy, Thomas RodetDiffusion Model Guidance Bayesian Inverse Problems
SATIE · SATIE Laboratory, ENS Paris-Saclay, CNRS, Universit´e Paris-Saclay, 91190 Gif-sur-Yvette, France
Generative Atmospheric Super-Resolution from Heterogeneous In Situ Observations through Composable Interfaces
Sep 24, 2026Yang Xu, Dibyajyoti Chakraborty, Haiwen Guan +2Bayesian Inverse Problems Data Assimilation
School of Mechanical Engineering, Purdue University, West Lafayette, Indiana, USA · College of Information Sciences and Technology, The Pennsylvania State University, University Park, Pennsylvania, USA
Variational objectives for amortized Bayesian inference in inverse problems: The role of posterior conditioning
Sep 21, 2026Abhishek Srivastava, Arijit Hazra, Rajesh DubbakuAmortized Inference Bayesian Inverse Problems
Department of Mechanical Engineering, Indian Institute of Technology Palakkad · Department of Mathematics, Indian Institute of Technology Palakkad
PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers
Sep 17, 2026Jiachen Yao, Zi-Siang Hsu, Xi Deng +5Uncertainty Quantification Bayesian Inverse Problems
California Institute of Technology · National Taiwan University · Lawrence Berkeley National Laboratory +3
Closed-form Bayesian homography estimation from noisy point correspondences
Sep 14, 2026Hanne Beuter, Sebastian DornMulti-View Geometry Uncertainty Quantification
Technische Hochschule Augsburg · TTZ Landsberg am Lech · Augsburg, Germany
Neural Posterior Estimation for Tomographic Weak Lensing Mass Mapping
Sep 7, 2026Tim White, Shreyas Chandrashekaran, Camille Avestruz +2Neural Posterior Estimation Bayesian Inverse Problems
Department of Statistics, University of Michigan · Department of Computer Science and Engineering, University of Michigan · Department of Physics, University of Michigan
Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem
Sep 3, 2026Yang Zhao, Junxiong Jia, Tao ZhouNormalizing Flows Bayesian Inverse Problems
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an 710049, China · Academy of Mathematics and Systems Sciences, Chinese Academy of Sciences, Beijing, 100190, China
A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
Aug 15, 2026Zhaoqiang Liu, Tongyao Pang, Ruibing Wang +1Diffusion Models for Image Restoration Bayesian Inverse Problems
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China · Yau Mathematical Sciences Center, Shuangqing Complex, Tsinghua University, Beijing 100084, China
Hybrid-Domain Posterior Sampling for Inverse Problems via Latent Flow Matching
Aug 1, 2026Hongjie Wu, Yiping Xie, Jiancheng LvBayesian Inverse Problems Image Inverse Problems
College of Computer Science, Sichuan University Chengdu, China
Normalizing Flows to Reconstruct Pseudo-PDFs
Jul 28, 2026Yamil Cahuana Medrano, Kostas OrginosNormalizing Flows Bayesian Inverse Problems
Department of Physics William & Mary Williamsburg, VA 23185
ELECTRIC: Evidential Learning-Enhanced CT Reconstruction via Iterative Correction
Jul 27, 2026Ge WangEvidential Deep Learning Bayesian Inverse Problems
Department of Biomedical Engineering Department of Electrical, Computer and Systems Engineering Department of Computer Science Rensselaer Polytechnic Institute, Troy, New York, USA
Inverse Bayesian Inference for Extracting Lesion Dynamics from Longitudinal Spectral CT
Jul 25, 2026Lukas Förner, Melina Wördehoff, Julian Steffens +6Latent Dynamics Modeling Bayesian Inverse Problems
Dept. of diagnostic and interventional Radiology and Neuroradiology, University Hospital Augsburg, Germany · Digital Medicine, University Hospital Augsburg, Germany · Chair for Computer-Aided Medical Procedures and Augmented Reality, Technical University of Munich, Germany +5
Priors learned from legacy reconstructions inherit undetectable overconfidence
Jul 23, 2026Ali Siahkoohi, Sina AlemohammadUncertainty Quantification Bayesian Inverse Problems
Department of Computer Science University of Central Florida Orlando, FL, USA · Department of Electrical and Computer Engineering The University of Texas at Austin Austin, TX, USA
Provable diffusion-based posterior sampling for linear inverse problems via DDIM
Jul 21, 2026Yuchen Jiao, Na Li, Changxiao Cai +2Diffusion Models for Image Restoration Bayesian Inverse Problems
Department of Statistics and Data Science, Chinese University of Hong Kong, Hong Kong · Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, USA · Department of Statistics and Data Science, the Wharton School, University of Pennsylvania, PA, USA
A Convex Approximation Framework for Neural Likelihood-Based Bayesian Inverse Problems
Jul 7, 2026Fabian Schneider, Tapio Helin, Leila TaghizadehBayesian Inverse Problems
Institute of Analysis and Scientific Computing, TU Wien, Vienna, Austria · School of Engineering Sciences, LUT University, Lappeenranta, Finland
Uncertainty-aware damage identification in short-span bridges via physics-informed variational autoencoder
Jul 6, 2026Ana Fernandez-Navamuel, A. Javier Omella, Diego Zamora-Sanchez +1Variational Autoencoders Uncertainty Quantification
Basque Center for Applied Mathematics (BCAM), Bilbao, Spain. · Departamento de Matematica Aplicada, Universidad de Zaragoza/IUMA, Zaragoza, Spain. · TECNALIA, Basque Research and Technology Alliance (BRTA), Parque Cientiﬁco y Tecnologico de Bizkaia, Astondo bidea, Ediﬁcio 700, Derio, E-48160, Spain. +1
Probabilistic Inversion with Flow Matching
Jun 30, 2026Baldur Paulwitz, Stefan BuskeFlow Matching Bayesian Inverse Problems
Institute of Geophysics and Geoinformatics, TU Bergakademie Freiberg
Measured-Subspace Consistency: A Plug-and-Play Operator for Diffusion Posterior Sampling in Accelerated MRI Reconstruction
Jun 26, 2026Junhyeok Lee, Kyu Sung ChoiBayesian Inverse Problems Accelerated MRI Reconstruction
Interdisciplinary Program in Cancer Biology, Seoul National University College of Medicine · Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital · Healthcare AI Research Institute, Seoul National University Hospital
Latent Diffusion Posterior Sampling with Surrogate Likelihood Guidance for PDE Inverse Problems
Jun 25, 2026Yuanzhe Wang, Alexandre M. TartakovskyLatent Diffusion Models Bayesian Inverse Problems
Department of Civil and Environmental Engineering University of Illinois Urbana-Champaign Urbana, IL 61801
What Do Flow-Based Inverse Solvers Approximate? A Posterior-Transport View
Jun 23, 2026Jian Xu, Delu Zeng, John Paisley +1Flow Matching Bayesian Inverse Problems
1RIKEN iTHEMS · 2RIKEN AIP · 3South China University of Technology +1
A Synthetic Reliability-Aware PINN Benchmark for Offshore Wind Turbine Support-Structure Monitoring with Bayesian Inverse Identification
Jun 23, 2026Puneet Kant, Monika TanwarNeural Surrogate Modeling Bayesian Inverse Problems
aSchool of Artificial Intelligence and Data Science, Indian Institute of Technology Jodhpur · bSchool of Management and Entrepreneurship, Indian Institute of Technology Jodhpur
Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems
Jun 21, 2026Yaozhong Shi, Zachary E. Ross, Yisong YueBayesian Inverse Problems Posterior Sampling
California Institute of Technology
Bayesian three-dimensional seismic travel-time tomography for active- and passive-source seismic data using physics-informed neural network
Jun 19, 2026Ryoichiro Agata, Kazuya Shiraishi, Gou Fujie +1Uncertainty Quantification Bayesian Inverse Problems
Japan Agency for Marine-Earth Science and Technology · Earth Science New Zealand

Oct 8, 2026, cs.LGJ/K move · Enter open · S save

Uncovering and Fixing Collider Bias in Bayesian PINNs

Michael Obermayr, Robert Peharz

TU Graz

Physics-Informed ML Bayesian Inverse Problems Hierarchical Bayesian Modeling

Open paper AskPDF arXiv

Bayesian physics-informed neural networks (B-PINNs) are a popular framework for parameter and state inference from sparse or noisy observations. They are commonly formulated via a collider structure, in which physical and trajectory parameters are assumed to be a priori independent and become coupled through virtual likelihoods on differential-equation residuals that enforce physical consistency. We show that this modeling choice can induce severe systematic bias in the posterior over physical parameters: even when the prior is favorably centered on the ground-truth parameters, the resulting posterior can drift away and concentrate far from them. As a remedy, we advocate a hierarchical chain model in which physics generates trajectories, which in turn generate observations. The chain model does not suffer from this posterior bias, but it poses a harder, so-called doubly intractable, inference problem due to a physics-dependent normalization constant. This challenge can be resolved by discretizing the underlying stochastic dynamics, after which the chain posterior can be sampled exactly with particle MCMC. We identify two distinct mechanisms characterizing the collider bias, derive analytical approximations of their magnitudes, and establish diagnostic criteria for predicting when standard B-PINNs remain reliable. Experiments confirm the predicted bias and show that the chain formulation successfully avoids it.

Momentum

Related topics

Latest papers 78